基于图像特征的雷达脉内调制类型识别  

Radar Intra-pulse Modulation Type Recognition Based on Image Features

作　　者：高君丰[1] 刘芬芬 GAO Junfeng;LIU Fenfen(No.92785 Troops of PLA,Qinhuangdao 066200;No.91404 Troops of PLA,Qinhuangdao 066000)

机构地区：[1]中国人民解放军92785部队,秦皇岛066200 [2]中国人民解放军91404部队,秦皇岛066000

出　　处：《舰船电子工程》2021年第7期97-101,共5页Ship Electronic Engineering

摘　　要：为了解决复杂体制下雷达脉内信号的识别问题,提出一种雷达脉内信号调制类型自动识别方法,首先对信号进行SPWVD时频变换,提取时频图像的中心矩和伪Zernike矩特征,然后将特征矢量输入到随机森林分类器中进行分类识别。仿真结果表明,该算法性能良好,能对常见的8种调制类型进行很好的识别。In order to solve the problem of radar intra-pulse signal recognition under a complex system,an automatic recogni⁃tion method of radar intra-pulse signal modulation type is proposed.First,SPWVD time-frequency transformation is performed on the signal,and the central moment and pseudo Zernike moment characteristics of the time-frequency image are extracted.Then the feature vector is entered into the random forest classifier for classification and recognition.The simulation results show that the algo⁃rithm has good performance and can recognize the 8 common modulation types well.

关 键 词：调制类型识别 时频变换 矩特征 随机森林 

分 类 号：TN975[电子电信—信号与信息处理]